Search

A pre-treatment process was evaluated in this work for wastewater from paper recycling using microwave technology followed by rapid precipitation of contaminants through centrifugation. Artificial neural networks (ANNs) were used to analyze and optimize the turbidity values. Thirty experimental runs were utilized including microwave (MW) power, duration, centrifuge time, and centrifuge speed as input variables, generated by the Central Composite Full Design (CCFD) approach. The experimental turbidity ranged from 8.1 to 19.7 NTU, while predicted values ranged from 8.4 to 19.7 NTU by ANN. The ANN model showed a robust prediction performance with low mean squared error values during training and testing. Moreover, high R² values showed a remarkable agreement between the experimental observations and ANN predictions. The results obtained from the input values (A:150.00, B:60.00, C:15.00, D:30.00) of sample 2, which gave the lowest turbidity value, showed the most removal of pollution. The results obtained from the input values (A:250.00, B:60.00, C:7.00, D:20.00) of sample 30, which gave the highest turbidity value, showed the least removal of pollution. The results showed that increasing RPM and time of the centrifugation process significantly affected the removal of pollution in wastewater. [ABSTRACT FROM AUTHOR]

This work reports the degradation of cellulosic material, i.e., paper, under different environmental conditions (soil and hydrolytic). Models were developed using central composite design (CCD) within the framework of response surface methodology (RSM) and artificial neural network (ANN) techniques. It is done as part of a solid waste management system to eliminate the waste produced by excessive paper usage and obtain optimized degradation conditions of paper. In view of the real environments where paper-based solid wastes are usually exposed, soil degradation and hydrolytic degradation of paper were investigated. The factors pH (4–10), compost ratio (2–5), CaCl2 (5–15 ppm), and time (7–20 days) were independent factors that varied for the study, and degradation conversion was measured as the dependent variable for soil degradation of paper. The factors pH (4–10), CaCl2 (2–5 ppm), tripotassium phosphate (TPP, 2–5 ppm), and time (6–16 days) were independent variables that varied for the study, and degradation conversion was the dependent variable for hydrolytic degradation of paper. The optimal conditions for soil degradation were determined to be a pH of 4, a compost ratio of 5, a salt (CaCl2) addition of 5 ppm, and a duration of 20 days, resulting in the highest observed conversion rate. The coefficient of regression (R2) for CCD is 87.24%, whereas it is 94.82% for ANN. The optimal conditions for achieving maximum conversion in hydrolytic degradation include a pH of 10, a CaCl2 salt concentration of 5 ppm, a TPP salt concentration of 2 ppm, and a duration of 16 days. The coefficient of regression for CCD is 75.15%, while the coefficient of regression for ANN is 93.91%. In both deterioration scenarios, the data exhibited a higher degree of fit when modeled using ANN compared to CCD (RSM). [ABSTRACT FROM AUTHOR]

The color gamut of imaging media is significant for the reproduction of color images because its magnitude directly affects the degree to which colors change during the printing process. Over the last few years, digital impression technology has started to play a substantial role in the printing industry due to the quest for short runs and variable information printing. The color gamut of electrophotographic digital printing depends on various parameters including the printer and toner, but especially the properties (whiteness, roughness, and gloss) of the paper, which influence the final printed color gamut and replication quality. Artificial intelligence approaches are applied herein for the first time to choose and predict the performance of a paper with appropriate properties to achieve the maximum color gamut. A genetic algorithm-based computer code is developed to optimize the architecture of an artificial neural network, thereby yielding an accurate model to predict the color gamut achievable in electrophotographic color printing. The gamut volume was generated using an Eye-One spectrophotometer, ProfileMaker, and ColorThink software. The properties of 11 dissimilar types of paper were assessed by atomic force microscopy, spectrophotometer, and goniophotometer. The results indicate that the reproducibility depended considerably on the features of the paper. Although high whiteness and gloss increased the color gamut volume, and high roughness decreased the reproducibility of the printing machine, the artificial intelligence approach provided the opportunity to achieve a high gamut volume with low gloss and high roughness. [ABSTRACT FROM AUTHOR]

Paper mills are among the most polluting industries, responsible for many organic and inorganic compounds emissions. The fibres electro-kinetic features strongly affect the ability to retain fillers since the fillers–fibres interactions are charge induced. The control and the prediction of these parameters would represent a precious aid for process management, allowing the fillers retention enhancement, a lower environmental impact and the paper sheet properties streamlining. The work presented deals with the implementation and training of four artificial neural networks (ANNs) for the prediction of the main electrochemical and physical features of cellulose pulp and paper. First, two ANNs predict the electrochemical parameters. Following, they were applied to predict the paper sheet properties and fillers retention. The neural models implemented showed outstanding prediction performance, with R2 in the order of 0.999 and a low mean error. The results demonstrate how Artificial Neural Networks may be a valuable instrument for paper mill pollutant reduction. However, they suggest a more inclusive investigation for a better fibres behaviour representation. • Main process parameters of an industrial papermaking process were identified. • Experimental datasets were achieved during industrial production. • Artificial Neural Networks were trained for process parameters prediction. • Accurate predictions of papermaking process were obtained. [ABSTRACT FROM AUTHOR]

An instrument-free, user-friendly, and cost-effective PAD colorimetric sensor that can quantitative detection of H 2 O 2 has been realized by using bimetallic nickel–cobalt selenides as highly active peroxidase mimic and smartphone integrated with dark cavity as detector. Integrated with an ANN model and a self-compiled easy-to-use smartphone APP, the intelligent and on-site detection of H 2 O 2 was constructed, which exhibited an ultra-wide dynamic range. [Display omitted] • An effective paper-based colorimetric sensor was prepared based on nanozyme. • The optimized Ni 0.75 Co 0.25 Se exhibited excellent peoxidase-mimetic activities. • The on-site detection of H 2 O 2 was constructed by a self-compiled smartphone APP. • The machine learning-assisted sensor can detect H 2 O 2 over a wide dynamic range. Paper-based analytical devices (PADs) integrated with smartphones have shown great potential in various fields, but they also face challenges such as single signal reading, complex data processing and significant environmental impacting. In this study, a colorimetric PAD platform has been proposed using bimetallic nickel–cobalt selenides as highly active peroxidase mimic, smartphone with 3D-printing dark-cavity as a portable detector and an artificial neural network (ANN) model as multi-signal processing tool. Notably, the optimized nickel–cobalt selenides (Ni 0.75 Co 0.25 Se with Ni to Co ratio of 3/1) exhibit excellent peoxidase-mimetic activities and are capable of catalyzing the oxidation of four chromogenic reagents in the presence of H 2 O 2. Using a smartphone with image capture function as a friendly signal readout tool, the Ni 0.75 Co 0.25 Se based four channel colorimetric sensing paper is used for multi-signal quantitative analysis of H 2 O 2 by determining the Grey, red (R), green (G) and blue (B) channel values of the captured pictures. An intelligent on-site detection method for H 2 O 2 has been constructed by combining an ANN model and a self-programmed easy-to-use smartphone APP with a dynamic range of 5 μM to 2 M. Noteworthy, machine learning-assisted smartphone sensing devices based on nanozyme and 3D printing technology provide new insights and universal strategies for visual ultrasensitive detection in a variety of fields, including environments monitoring, biomedical diagnosis and safety screening. [ABSTRACT FROM AUTHOR]

Electronic nose systems when deployed in network mesh can effectively provide a low budget and onsite solution for the industrial obnoxious gaseous measurement. For accurate and identical prediction capability by all the electronic nose systems, a reliable calibration transfer model needs to be implemented in order to overcome the inherent sensor array variability. In this work, robust regression (RR) is used for calibration transfer between two electronic nose systems using a Box–Behnken (BB) design. Out of the two electronic nose systems, one was trained using industrial gas samples by four artificial neural network models, for the measurement of obnoxious odours emitted from pulp and paper industries. The emissions constitute mainly of hydrogen sulphide (H 2 S), methyl mercaptan (MM), dimethyl sulphide (DMS) and dimethyl disulphide (DMDS) in different proportions. A Box–Behnken design consisting of 27 experiment sets based on synthetic gas combinations of H 2 S, MM, DMS and DMDS, were conducted for calibration transfer between two identical electronic nose systems. Identical sensors on both the systems were mapped and the prediction models developed using ANN were then transferred to the second system using BB–RR methodology. The results showed successful transmission of prediction models developed for one system to other system, with the mean absolute error between the actual and predicted concentration of analytes in mg L −1 after calibration transfer (on second system) being 0.076, 0.1801, 0.0329, 0.427 for DMS, DMDS, MM, H 2 S respectively. [ABSTRACT FROM AUTHOR]

Genomic signal processing is a development field in medicine and agriculture. Numerous research areas are processing the genomics of living organism such as animals and particularly human beings. In this paper, the microarray data set for the biological organism which includes a large number of gene data has taken for the processing. The microarray data are a powerful technology practised in the research field for validating the gene discovery and diagnosis of diseases. The data are processed to a large number with plenty of genes. The proposed Kalman filter-based fuzzy c-means cluster and artificial neural network (KF-FANN) enhance the genomic signal processing to the optimal level. The Kalman filter proposed in this paper to remove the noise and smoothen the data for signal processing. An ideal clustering process is carried out for the classification of the microarray data. The fuzzy c-means clustering was proposed in this paper for grouping the microarray after removing the noise. The artificial neural network is a biologically inspired model proposed in this work for the classification of microarray data to point out the normal and abnormal genes in the microarray data. The proposed work has compared with existing techniques such as c-means, k-means clustering, and multi-SVM, respectively. The proposed method is carried out in the MATLAB platform, and results are evaluated in terms of Calinski–Harabasz index, separation index, Xie and Beni's index, partition index, accuracy, precision, recall, and F-score. The analysed result shows that the proposed KF-FANN is an efficient method for the classification of microarray data than existing approaches in genomic signal processing. [ABSTRACT FROM AUTHOR]

In the recent era, Transportation considers the most powerful component of the business logistics system. Likewise, there is an interdependent relationship between the transportation and logistics systems. This paper aims to make a comparative study of logistics transportation problems based on intelligence algorithms. The researchers surveyed the previous studies conducted in the Artificial Intelligent field to solve complex problems. In this research study, the authors focused on techniques that are mostly applied in transportation and logistics systems, especially, Artificial Neural Network, Genetic Algorithm, and Fuzzy Logic models. Also, a proposed model and algorithm was done to obtain customers' and organizations' satisfaction. Artificial Neural Network uses as a decision tool that combines the system stat sets and the operation state-dependent sets. As well, the genetic algorithm combines the best parameters as a method to finds the best evaluation solutions. And fuzzy logic uses a fuzzy set to help decision-makers in making the best decisions in multiple fields. Finally, authors recommended to work in two new areas which are FGA, NFGA Algorithms to solve complex and multimodal problems that faces transportation logistics sector. [ABSTRACT FROM AUTHOR]

The use of externally bonded composite systems is recognized as an effective solution for strengthening existing reinforced concrete (RC) structures. Steel-reinforced grout (SRG) is an attractive option, because of its compatibility with the concrete substrate and mechanical properties. However, a critical aspect is the delamination that might affect the steel textile–mortar and the mortar–concrete substrate interfaces. An experimental and theoretical investigation of the SRG–concrete bond is reported in this paper. In particular, the bond performances of SRG-to-concrete joints, which varies the width of the SRG fabric, the displacement rate, and the applied load eccentricity, are analyzed for the stress that is associated with the bond capacity, slip, and failure modes based on the results that are obtained by direct single-lap shear tests. To assess a data set for model calibration, the findings of this paper and those in the technical literature are collected. Therefore, a machine learning (ML) approach that is based on an artificial neural networks (ANN) algorithm is implemented, and a new analytical formulation for the prediction of the SRG-to-concrete bond capacity is proposed. [ABSTRACT FROM AUTHOR]

Flow processes onboard ships are common in order to transport fluids like oil, gas, and water. These processes are controlled by PID controllers, acting on the regulation valves as actuators. In case of a malfunction or refitting, a PID controller needs to be re-adjusted for the optimal control of the process. To avoid experimenting on operational real systems, models are convenient alternatives. When real-time information is needed, digital twin (DT) concepts become highly valuable. The aim of this paper is to analyze and determine the optimal NARX model architecture in order to achieve a higher-accuracy model of a ship's flow process. An artificial neural network (ANN) was used to model the process in MATLAB. The experiments were performed using a multi-start approach to prevent overtraining. To prove the thesis, statistical analysis of the experimental results was performed. Models were evaluated for generalization using mean squared error (MSE), best fit, and goodness of fit (GoF) measures on two independent datasets. The results indicate the correlation between the number of input delays and the performance of the model. A permuted k-fold cross-validation analysis was used to determine the optimal number of voltage and flow delays, thus defining the number of model inputs. Permutations of training, test, and validation datasets were applied to examine bias due to the data arrangement during training. [ABSTRACT FROM AUTHOR]

This paper presents an indoor positioning strategy based on Visible Light Communication that relies on LED luminaires as transmitters, whose luminous flux is modulated at different frequencies, and a light sensor as a receiver. Then, a previously trained Artificial Neural Network (ANN) uses the illuminance signal gathered by the receiver as input to estimate the sensor's position. The main contribution of the technique is that the ANN is trained by using an illuminance estimator based on the lighting distribution of the luminaires, which is obtained through the IES file provided by the luminaire's manufacturer, without the need to collect data from the environment. In this work, the designed illuminance estimator is validated by comparing it to the well-known commercial software DIALux and Relux. The algorithm's setting and the performance evaluation of the ANN are explained. Then, the impact of the lighting uniformity and the environment's number of divisions on the accuracy of the results is analyzed. Error analyses are also made by adding uncertainty to the illuminance measurements obtained by the sensor. Finally, the work is compared to several papers in the field. [ABSTRACT FROM AUTHOR]

This paper presents a vibration-based damage identification method that utilises a 'damage fingerprint' of a structure in combination with Principal Component Analysis (PCA) and neural network techniques to identify defects. The Damage Index (DI) method is used to extract unique damage patterns from a damaged beam structure with the undamaged structure as baseline. PCA is applied to reduce the effect of measurement noise and optimise neural network training. PCA-compressed DI values are, then, used as inputs for a hierarchy of neural network ensembles to estimate locations and severities of various damage cases. The developed method is verified by a laboratory structure and numerical simulations in which measurement noise is taken into account with different levels of white Gaussian noise added. The damage identification results obtained from the neural network ensembles show that the presented method is capable of overcoming problems inherent in the conventional DI method. Issues associated with field testing conditions are successfully dealt with for numerical and the experimental simulations. Moreover, it is shown that the neural network ensemble produces results that are more accurate than any of the outcomes of the individual neural networks. [ABSTRACT FROM AUTHOR]

Active distribution grids that contain energy sources (so-called distributed generation or DG) are nowadays a reality. Besides the many benefits DGs bring to the distribution grid, some challenges are associated with their integration. Since there are DGs now in the distribution grid, the occurrence of islanding operation is possible. Since an islanding operation can be dangerous, it is necessary to have an effective method to detect it. In the last decade, scientists have made a great effort to develop and test various islanding detection methods (IDMs). Many approaches have been tested, and the methods based on computational intelligence (CI) have shown great potential. Among them, artificial neural networks (ANNs) gained most of the research attention. This paper focuses on ANN application for islanding detection. It gives an exhaustive review of the ANN types used for islanding detection, the types of input data, and their transformation to fit the ANNs. Furthermore, various applications based on specific input data, preprocessing types, different learning algorithms, real-time implementation, and various distribution models used for ANN are reviewed. This paper investigates the potential of ANNs to enhance islanding detection accuracy, reduce non-detection zone (NDZ), and contribute to an overall efficient detection method. [ABSTRACT FROM AUTHOR]

This scientific paper explores the use of correlation coefficients of vibration signals and machine learning algorithms for structural damage assessment in beams under moving loads. The paper discusses the challenges of maintaining structural integrity and the importance of automated, nondestructive monitoring techniques. Preprocessing techniques, such as the random decrement technique (RDT), are highlighted for improving data analysis. Machine learning algorithms are identified as valuable tools for structural damage assessment. The paper concludes by emphasizing the potential of machine learning in safeguarding critical infrastructures. The text also discusses trigger points and the vibration response of a slender beam under a moving load. An artificial neural network (ANN) is proposed as a computational model for identifying non-linear features. Experimental testing on a simulated bridge girder using accelerometers collected data to identify and locate damage in the beam. The ANN achieved high accuracy in detecting damage appearance and location, but further research is needed to improve accuracy in real-world situations. [Extracted from the article]

This paper introduces a novel design for a universal DC-DC and DC-AC converter tailored for DC/AC microgrid applications using Approximate Dynamic Programming and Artificial Neural Networks (ADP-ANN). The proposed converter is engineered to operate efficiently with both low-power battery and single-phase AC supply, utilizing identical side terminals and switches for both chopper and inverter configurations. This innovation reduces component redundancy and enhances operational versatility. The converter's design emphasizes minimal switch usage while ensuring efficient conversion to meet diverse load requirements from battery or AC sources. A conceptual example illustrates the design's principles, and comprehensive analyses compare the converter's performance across various operational modes. A test bench model, rated at 3000W, demonstrates the converter's efficacy in all five operational modes with AC/DC inputs. Experimental results confirm the system's robustness and adaptability, leveraging ADP-ANN for optimal performance. The paper concludes by outlining potential applications, including microgrids, electric vehicles, and renewable energy systems, highlighting the converter's key advantages such as reduced complexity, increased efficiency, and broad applicability. [ABSTRACT FROM AUTHOR]

This research paper explores the realm of fault detection in distributed motors through the vision of the Internet of electrical drives. This paper aims at employing artificial neural networks supported by the data collected by the Internet of distributed devices. Cross-verification of results offers reliable diagnosis of industrial motor faults. The proposed methodology involves the development of a cyber–physical system architecture and mathematical modeling framework for efficient fault detection. The mathematical model is designed to capture the intricate relationships within the cyber–physical system, incorporating the dynamic interactions between distributed motors and their edge controllers. Fast Fourier transform is employed for signal processing, enabling the extraction of meaningful frequency features that serve as indicators of potential faults. The artificial neural network based fault detection system is integrated with the solution, utilizing its ability to learn complex patterns and adapt to varying motor conditions. The effectiveness of the proposed framework and model is demonstrated through experimental results. The experimental setup involves diverse fault scenarios, and the system's performance is evaluated in terms of accuracy, sensitivity, and false positive rates. [ABSTRACT FROM AUTHOR]

Integrating photovoltaic systems (PV) into the grid has garnered significant attention due to increasing interest in renewable energy sources. Maximizing the PV systems output power is crucial for improving energy efficiency and reducing operating costs. This paper presents a comparative analysis of two different techniques of maximum power point tracking (MPPT): perturb and observe (P&O) and artificial neural network (ANN) MPPT, focusing on their application in grid-connected PV systems. The paper evaluates their performance under various operating conditions, including changes in irradiance and temperature, that are discussed in three cases. The comparative analysis includes metrics such as voltage regulation and power loss. MATLAB Simulink is utilized to implement P&O and ANN MPPT methods, which include a PV cell connected to an MPPT-controlled boost converter. The simulation demonstrates the power loss of the PV model as well as the voltage regulation in the three cases for the two methods. The results obtained in simulation and implementations show that the ANN method outperforms the P&O in the three cases discussed in terms of power loss, voltage regulation, and efficiency. The results also show that the change in output power from PV is noticeable when compared to changes in radiation, while the change is slight when temperatures change. [ABSTRACT FROM AUTHOR]

The early detection of pests in plants and crops is essential for the production of good quality food. Computer vision techniques can be applied for the early detection of pests and which can minimise the pesticides used on the plants. Among many pests, white flies, mites, aphids and thrips are the most hazardous pests that affect the leaves. This paper presents an automated approach for the detection of different types of pests from leaf images of plants. The images of the plant leaves were acquired using a digital camera. Image pre-processing techniques, such as noise removal, filtering and contrast enhancement, are used for improving the quality of the images. Then, the k-means clustering method and global thresholding were used for segmenting the pests from the infected leaves. Textural features are extracted from those segmented images by statistical feature extraction methods. Artificial Neural Network (ANN) and Binary Support Vector Machine (SVM) classifiers were used to classify the unaffected leaf images from the pest affected leaf images and a multi-SVM classifier was used to identify the different types of pests. [ABSTRACT FROM AUTHOR]

In this paper, we propose a learning model for tracking the isolines of fluid based on the physical properties of particles in particle-based fluid simulations. Our method involves analyzing which weights, closely related to surface tracking among the various physical properties of fluid particles, are significant. These weights are used as input values for the learning algorithm, enabling relatively accurate isoline tracking. In addition, compared to existing learning models such as linear regression, LSTM (long short-term memory), and learning representation (1-layer) models, our method obtained superior surface tracking results without accumulating errors. By using our proposed network structure to track the fluid surface, it learns and predicts values derived from existing fluid simulation algorithms, eliminating the need for computational processes for level-set values and enabling real-time surface tracking. As the scale of the simulation increases, our method significantly reduces the time and resources consumed compared to traditional methods and can track the fluid surface without additional resource consumption. Furthermore, due to our method's simple network structure, the time consumed in the initial process of loading the model into memory is faster than models such as CNN and LSTM. Our proposed model occupies less than 30 kb of storage space, making it suitable for use in middleware. Lastly, to verify the generality of our method, we conducted tests in a total of five scenes, and in all test scenes, visually natural fluid isolines were represented. [ABSTRACT FROM AUTHOR]

The life expectancy of power transformers is primarily determined by the integrity of the insulating oil and cellulose paper between the conductor turns, phases and phase to earth. During the course of their in-service lifetime, the solid insulating system of windings is contingent on long-standing ageing and decomposition. The decomposition of the cellulose paper insulation is strikingly grievous, as it reduces the tensile strength of the cellulose paper and can trigger premature failure. The latter can trigger premature failure, and to realize at which point during the operational life this may occur is a daunting task. Various methods of estimating the DP have been proposed in the literature; however, these methods yield different results, making it difficult to accurately estimate a reliable DP. In this work, a novel approach based on the Feedforward Backpropagation Artificial Neural Network has been proposed to predict the amount of DP in transformer cellulose insulation. Presently, no ANN model has been proposed to predict the remaining DP using 2FAL concentration. A databank comprising 100 data sets—70 for training and 30 for testing—is used to develop the proposed ANN using 2-furaldehyde (2FAL) as an input and DP as an output. The proposed model yields a correlation coefficient of 0.958 for training, 0.915 for validation, 0.996 for testing and an overall correlation of 0.958 for the model. [ABSTRACT FROM AUTHOR]

Detecting instruments in a music signal is often used in database indexing, song annotation, and creating applications for musicians and music producers. Therefore, effective methods that automatically solve this issue need to be created. In this paper, the mentioned task is solved using mel-frequency cepstral coefficients (MFCC) and various architectures of artificial neural networks. The authors' contribution to the development of automatic instrument detection covers the methods used, particularly the neural network architectures and the voting committees created. All these methods were evaluated, and the results are presented and discussed in the paper. The proposed automatic instrument detection methods show that the best classification quality was obtained for an extensive model, which is the so-called committee of voting classifiers. [ABSTRACT FROM AUTHOR]

Drinking water treatment is a complex system of chemical, physical, and biological processes that is highly dependent on water quality and the design of the treatment process. To create decision-support tools, the prediction of key performance indicators, such as settled water turbidity, is needed. A variety of data-driven modeling techniques is available to formulate such predictions. Datadriven models provide valuable tools for formulating predictions where there is a lack of mechanistic models or the mechanisms are not fully understood, as in surface water treatment. The objective of this paper is to evaluate and compare the effectiveness of various data-driven techniques for this important, but difficult, problem. Recognizing that the size and quality of the dataset are most critical in this kind of analysis, this work uses one of the largest datasets used in this context consisting of 2,527 vectors of water quality and operational data (2,527 X nine data frame) from a full-scale water treatment plant. The paper constructs and compares the performance of the several data-driven models including k-nearest neighbor (KNN) regression, polynomial regression, and artificial neural networks (ANN). Based on test scaled root mean square error (RMSE), the ANN model was the most predictive (0.124). Similarly, the ANN model had the best predictive performance based on total scaled RMSE (0.086). These results show that ANNs have a high potential for the development of a future decision support system in selecting appropriate coagulant doses based on settled water turbidity. [ABSTRACT FROM AUTHOR]

The retinal impulse signal is the basic carrier of visual information. It records the distribution of light on the retina. However, its direct conversion to a scene image is difficult due to the nonlinear characteristics of its distribution. Therefore, the use of artificial neural network to reconstruct the scene from retinal spikes has become an important research area. This paper proposes the architecture of a neural network based on vector quantization, where the feature vectors of spike trains are extracted, compressed, and stored using a feature extraction and compression network. During the decoding process, the nearest neighbour search method is used to find the nearest feature vector corresponding to each feature vector in the feature map. Finally, a reconstruction network is used to decode a new feature map composed of matching feature vectors to obtain a visual scene. This paper also verifies the impact of vector quantization on the characteristics of pulse signals by comparing experiments and visualizing the characteristics before and after vector quantization. The network delivers promising performance when evaluated on different datasets, demonstrating that this research is of great significance for improving relevant applications in the fields of retinal image processing and artificial intelligence. [ABSTRACT FROM AUTHOR]

This study presents a numerical approach to the design and optimization of centrifugal impellers used in the pumps of active thermal control systems of spacecraft. Although launch costs have shrunk in the last decade, the performance requirements, such as efficiency and reliability, have increased, as such systems are required to work up to 15 years, depending on the mission. To that effect, our paper deals with the first step in this pump design, namely the hydraulic optimization of the impeller. Constructively, this type of impeller allows for certain balancing systems and labyrinth seals to be applied in a more effective way, as well as allowing for additive manufacturing methods to be used—however, details regarding these aspects are beyond the scope of the current paper. By combining empirical formulas, computational fluid dynamics (CFD) analysis, and artificial neural networks (ANNs), the research focuses on achieving high efficiency and fast manufacturing. A series of geometries have been sized and validated using steady-state RANS (Reynolds Averaged Navier-Stokes) simulations, leading to the identification of the most efficient configuration. Subsequent optimization using an ANN resulted in a refined impeller design with notable improvements in hydraulic performance: a 3.55% increase in efficiency and a 7.9% increase in head. Key parameters influencing impeller performance, including blade number, incidence, and backsweep angles, are identified. This approach offers a comprehensive method to address the evolving requirements of space missions and contributes to the advancement of centrifugal pump technology in the space domain. [ABSTRACT FROM AUTHOR]

Structural health monitoring is extremely important for sustaining and preserving the service life of civil structures. Research to identify the damage can detect, locate, quantify and, where appropriate, predict potential structural damage. This paper is about damage identified by non-destructive vibrationbased experiments, which uses the difference between modal frequencies and deflection of an initial and damaged structure. The main objective of this paper is to present a hybrid method for structural damage identification combining artificial neural network and aimed multilevel sampling method. The combination of these approaches yields a more efficient damage identification in terms of time and accuracy of damage localization and damage extent determination. [ABSTRACT FROM AUTHOR]

The propulsion system for an aircraft is one of its most crucial systems; therefore, its reliable work must be ensured during all operational conditions and regimes. Modern materials, techniques and methods are used to ensure this goal; however, there is still room for improvement of this complex system. The proposed manuscript describes a progressive approach for the mechanical properties prediction of the turbine section during jet engine operation using an artificial neural network, and it illustrates its application on a small experimental jet engine. The mechanical properties are predicted based on the measured temperature, pressure and rpm during the jet engine operation, and targets for the artificial neural network are finite element analyses results. The artificial neural network (ANN) is trained using training data from the experimental measurements (temperatures, pressure and rpm) and the results from finite element analyses of the small experimental engine turbine section proposed in the paper. The predicted mechanical stress by ANN achieved high accuracy in comparison to the finite element analyses results, with an error of 1.38% for predicted mechanical stress and correlation coefficients higher than 0.99. Mechanical stress and deformation prediction of the turbine section is a time-consuming process when the finite element method is employed; however, the method with artificial neural network application presented in this paper decreased the solving time significantly. Mechanical structural analyses performed in ANSYS software using finite element modeling take around 30–40 min for one load step. In contrast, the artificial neural network presented in this paper predicts the stress and deformation for one load step in less than 0.00000044 s. [ABSTRACT FROM AUTHOR]

Abnormal behavior is called an abnormal behavior that deviates from the same normal standard as the average. The installation of public CCTVs to prevent crimes is increasing, but the crime rate is rather increasing recently. In line with this situation, artificial intelligence research using deep learning that automatically finds abnormal behavior in CCTV is increasing. Deep learning is a type of artificial intelligence designed based on artificial neural networks, and the quality of learning data is important for high accuracy in the development of artificial intelligence through deep learning. This paper verifies whether learning data for abnormal behavior detection is suitable as learning data which is being constructed using an MPED-RNN model for binary classification to determine whether there is an abnormal behavior by frame using skeleton data of a person based on an autoencoder. As a result of the experiment, the unsupervised learning-based MPED-RNN model used in this paper is not suitable for verifying images with a similar number of frames with and without abnormal behavior, such as the corresponding data, and it is judged that appropriate results can be derived only when verified with a supervised learningbased model. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) driven systems have been sharply growing in the recent times but this evolution is hampered by cybersecurity threats like spoofing, denial of service (DoS), distributed denial of service (DDoS) attacks, intrusions, malwares, authentication problems or other fatal attacks. The impacts of these security threats can be diminished by providing protection towards the different IoT security features. Different technological solutions have been presented to cope with the vulnerabilities and providing overall security towards IoT systems operating in numerous environments. In order to attain the full-pledged security of any IoT-driven system the significant contribution presented by artificial neural networks (ANNs) is worthy to be highlighted. Therefore, a systematic approach is presented to unfold the efforts and approaches of ANNs towards the security challenges of IoT. This systematic literature review (SLR) is composed of three (3) research questions (RQs) such that in RQ1, the major focus is to identify security requirements or criteria that defines a full-pledge IoT system. This question also focusses on pinpointing the different types of ANNs approaches that are contributing towards IoT security. In RQ2, we highlighted and discussed the contributions of ANNs approaches for individual security requirement/feature in comprehensive and detailed fashion. In this question, we also determined the various models, frameworks, techniques and algorithms suggested by ANNs for the security advancements of IoT. In RQ3, different security mechanisms presented by ANNs especially towards intrusion detection system (IDS) in IoT along with their performances are comparatively discussed. In this research, 143 research papers have been used for analysis which are providing security solutions towards IoT security issues. A comprehensive and in-depth analysis of selected studies have been made to understand the current research gaps and future research works in this domain. [ABSTRACT FROM AUTHOR]

The reliability of thimble tubes plays a critical role for maintaining the safety of a nuclear power plant. The defect depth needs to be quantified and predicted to support the operational decision-making. This paper presents a method to quantify the defects on thimble tube wall based on the analyzation of eddy current testing (ECT) data. Then, a method using artificial neural network (ANN) to predict the detect depth is studied. The tubes are divided into 2 shapes and four regions according to their positions and the data of each region and each shape is expanded by mean interpolation. A prediction model based on ANN is constructed for each shape in each region. The experimental results show that the model can predict the signal of the next year according to the signal of the previous three years with mean absolute percentage error less than 16%. [ABSTRACT FROM AUTHOR]

Electricity consumption in buildings is one of the major causes of energy usage and knowledge of this can help building owners and users increase energy efficiency and conservation efforts. For Pacific Island countries, building electricity demand data is not readily accessible or available for constructing models to predict electricity demand. This paper starts to fill this gap by studying the case of schools in Fiji. The aim of the paper is to assess the factors affecting electricity demand for grid-connected Fijian schools and use this assessment to build mathematical models (multiple linear regression (MLR) and artificial neural network (ANN)) to predict electricity consumption. The average grid-connected electricity demand in kWh/year was 1411 for early childhood education schools, 5403 for primary schools, and 23,895 for secondary schools. For predicting electricity demand (ED) for all grid-connected schools, the stepwise MLR model shows that taking logarithm transformations on both the dependent variable and independent variables (number of students, lights, and air conditioning systems) yields statistically significant independent variables with an R2 value of 73.3% and RMSE of 0.2248. To improve the predicting performance, ANN models were constructed on both the natural form of variables and transformed variables. The optimum ANN model had an R2 value of 95.3% and an RMSE of 59.4 kWh/year. The findings of this study can assist schools in putting measures in place to reduce their electricity demand, associated costs, and carbon footprint, as well as help government ministries make better-informed policies. [ABSTRACT FROM AUTHOR]

There are various techniques for separating natural gas liquid (NGL) from natural gas, one of which is refrigeration. In this method, the temperature is reduced in the dew point adjustment stage to condense the NGLs. The purpose of this paper is to introduce a methodology for optimizing the NGLs production process by determining the optimal values for specific set-points such as temperature and pressure in various vessels and equipment. The methodology also focuses on minimizing energy consumption during the NGL production process. To do this, this research defines a multi-objective problem and presents a hybrid algorithm, including a genetic algorithm (NSGA II) and artificial neural network (ANN) system. We solve the defined multi-objective problem using NSGA II. In order to design a tool that is a decision-helper for selecting the appropriate set-points, the ability of the ANN algorithm along with multi-objective optimization is evaluated. We implement our proposed algorithm in an Iranian chemical factory, specifically the NGL plant, which separates NGL from natural gas, as a case study for this article. Finally, we demonstrate the effectiveness of our proposed algorithm using the nonparametric statistical Kruskal-Wallis test. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to evaluate the performance of the multiple linear regression (MLR) using a fixed-effects model (FE) and artificial neural network (ANN) models to predict the level of customer deposits on a sample of Tunisian commercial banks. Design/methodology/approach: Training and testing datasets are developed to evaluate the level of customer deposits of 15 Tunisian commercial banks over the 2002–2021 period. This study uses two predictive modeling techniques: the MLR using a FE model and ANN. In addition, it uses the mean absolute error (MAE), R-squared and mean square error (MSE) as performance metrics. Findings: The results prove that both methods have a high ability in predicting customer deposits of 15 Tunisian banks. However, the ANN method has a slightly higher performance compared to the MLR method by considering the MAE, R-squared and MSE. Practical implications: The findings of this paper will be very significant for banks to use additional management support to forecast the level of their customers' deposits. It will be also beneficial for investors to have knowledge about the capacity of banks to attract deposits. Originality/value: This paper contributes to the existing literature on the application of machine learning in the banking industry. To the author's knowledge, this is the first study that predicts the level of customer deposits using banking specific and macroeconomic variables. [ABSTRACT FROM AUTHOR]

Super-computing or HPC clusters are built to provide services to execute computationally complex applications. Generally, these HPC applications involve large scale IO (input/output) processing over the networked parallel file system disks. They are commonly developed on top of the C/C++ based MPI standard library. The HPC clusters MPI–IO performance significantly depends on the particular parameter value configurations, not generally considered when writing the algorithms or programs. Therefore, this leads to poor IO and overall program performance degradation. The IO is mostly left to individual practitioners to be optimised at code level. This usually leads to unexpected consequences due to IO bandwidth degradation which becomes inevitable as the file data scales in size to petabytes. To overcome the poor IO performance, this research paper presents an approach for auto-tuning of the configuration parameters by forecasting the MPI–IO bandwidth via artificial neural networks (ANNs), a machine learning (ML) technique. These parameters are related to MPI–IO library and lustre (parallel) file system. In addition to this, we have identified a number of common configurations out of numerous possibilities, selected in the auto-tuning process of READ/WRITE operations. These configurations caused an overall READ bandwidth improvement of 65.7% with almost 83% test cases improved. In addition, the overall WRITE bandwidth improved by 83% with number of test cases improved by almost 93%. This paper demonstrates that by using auto-tuning parameters via ANNs predictions, this can significantly impact overall IO bandwidth performance. [ABSTRACT FROM AUTHOR]

The introduction of hybrid alternating current (AC)/direct current (DC) distribution networks led to several developments in smart grid and decentralized power system technology. The paper concentrates on several topics related to the operation of hybrid AC/DC networks. Such as optimization methods, control strategies, energy management, protection issues, and proposed solutions. The implementation of neural network optimization methods has great importance for the successful integration of multiple energy sources, dynamic energy management, establishment of system stability and reliability, power distribution optimization, management of energy storage, and online fault detection and diagnosis in hybrid networks like the hybrid AC–DC microgrids (MG). Taking advantage of renewable energy generation and cost-cutting through the neural network optimization technique holds the key to these progressions. Besides identifying the challenges in the operation of a hybrid system, the paper also compares this system to conventional MGs and shows the benefits of this type of system over different MG structures. This review compares the different topologies, particularly looking at the AC–DC coupled hybrid MGs, and shows the important role of the interlinking of converters that are used for efficient transmission between AC and DC MGs and generally used to implement the different control and optimization techniques. Overall, this review paper can be regarded as a reference, pointing out the pros and cons of integrating hybrid AC/DC distribution networks for future study and improvement paths in this developing area. [ABSTRACT FROM AUTHOR]

This paper studies an artificial neural network (ANN) for multi-asset European options. Firstly, a simple three-layer ANN-3 is established with undetermined weights and bias. Secondly, the time–space discrete PDE of the multi-asset option is given and the corresponding discrete data are fed into the ANN-3. Then, using least squares error as the objective function, the weights and bias of ANN-3 are trained well. Numerical examples are carried out to confirm the stability, accuracy and efficiency. Experiments show the ANN's relative error is about  0.8 % . This method can be extended into multi-layer ANN- q (q > 3)  and extended into American options. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) can be used for accurate heat load forecasting in district heating systems (DHSs). This paper presents an application of a shallow ANN with two hidden layers in the case of a local DHS. The developed model was used to write a simple application in Python 3.10 that can be used in the operation of a district heating plant to carry out a preliminary analysis of heat demand, taking into account the ambient temperature on a given day. The model was trained using the real data from the period 2019–2022. The training was sufficient for the number of 150 epochs. The prediction effectiveness indicator was proposed. In the considered case, the effectiveness of the trained network was 85% and was better in comparison to five different regression models. The developed tool was based on an open-source programming environment and proved its ability to predict heating load. [ABSTRACT FROM AUTHOR]

To address the problem that the traditional detection method for litchi sugar content is time-consuming and laborious and will destroy the tested sample, this paper proposed a non-destructive detection method for litchi sugar content based on near-infrared spectroscopy (NIR) and artificial intelligence algorithm. Firstly, to remove noise and other interference, the preprocessing methods for spectral data are studied. Nine preprocessing methods, such as moving average smoothing (MA), standard normal variate transform (SNV), and multiplicative scatter correction (MSC), are adopted to preprocess the spectral data. Then, to reduce the input dimension of the model and overcome the interference of redundant bands, the feature extraction methods for spectral data are examined. Two feature extraction methods, including Monte-Carlo uninformative variable elimination (MCUVE) and competitive adaptive reweighted sampling (CARS), are utilized to extract the features of spectral data. Finally, partial least squares regression (PLSR) and stochastic configuration network (SCN) are adopted to establish the prediction model of litchi sugar content. The experimental results show that the SNV-CARS-SCN prediction model has the highest accuracy. The coefficient of determination ( R 2 ), RMSE, and MAE of the training dataset are 0.9996, 0.1145, and 0.1154, respectively. R 2 , RMSE, and MAE of the test dataset are 0.9740, 0.4962, and 0.3818, respectively. The NIR detection system and SCN prediction model designed in this paper are of great significance for the design of litchi automatic sorting system. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) tunes modern technologies, including wireless sensors and cloud computing, to create a homogeneous and highly effective environment. Therefore, IoT has emerged in various fields of life, such as healthcare, industry, and agriculture. Agriculture is among the primary components of developing nations' financial states and is vital in maintaining human life. However, the human capacity to reproduce far exceeds the capability of our planet to secure the food required for our lives. Hence, the emergence of IoT in this industry has seen essential advancements to help boost agriculture production and quality. In addition, this emergence exposes the smart agriculture environment to considerable cyber threats. This paper presents a network intrusion detection system (NIDS) to mitigate smart agriculture security vulnerabilities. We developed our framework using radial basis functions neural networks (RBFNN) to detect and classify intrusions in the IoT network. To get our model to perform in its best form, we applied crowd wisdom tree-based machine learning (ML) techniques to select relevant features from the datasets, such as random Forrest (RF), AdaBoost (ADA), extra trees (ET), LightGBM (LGBM), and XGBoost (XGB). We implemented a single-class support vector machine (1-CSVM) to detect and remove outliers. We evaluated our model using NF-Bot-IoT and NF-ToN-IoT datasets. It scored 99.25% accuracy (ACC) and 82.97% Matthews correlation coefficient (MCC) and 90.05% MCC and 96.92% ACC on preprocessed NF-Bot-IoT and NF-ToN-IoT, respectively. Our model showed outstanding performance in overcoming the NF-Bot-IoT dataset imbalance. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid data‐driven and physics‐based simulation technique for seismic response evaluation of steel Buckling‐Restrained Braced Frames (BRBFs) considering brace fracture. Buckling‐Restrained Brace (BRB) fracture is represented by cumulative plastic deformation capacity. A dataset, consisting of 95 past BRB laboratory tests and 120 simulated BRB responses generated using the finite element method, is first developed. An Artificial Neural Network‐based (ANN) predictive model is then trained using the training dataset to estimate the cumulative plastic deformation of BRBs. The prediction capability of the ANN‐based predictive model is validated using the training dataset and an existing regression‐based predictive model. In the second part of the paper, an hybrid simulation technique combining the data‐driven model and physics‐based numerical modeling is presented to conduct the nonlinear time history analysis, followed by 1) validation against a full‐scale BRBF testing and 2) demonstration of the proposed simulation technique using a six‐story BRBF. The results confirm that the proposed predictive model can predict the BRB fracture with sufficient accuracy. Furthermore, the hybrid data‐driven physics‐based simulation technique can be used as a powerful tool for dynamic analysis of BRBFs considering BRB fracture. [ABSTRACT FROM AUTHOR]

Surface waters are essential for meeting the needs of the world. In many regions, stream water quality is a major concern due to contamination from multiple sources. Stream water is also susceptible to climatic events and land-use practices influencing its catchment. Understanding the impact of such events on stream water quality is crucial for managing and protecting aquatic ecosystems and providing safe drinking water to communities that rely on these streams. Hence, monitoring and evaluating stream water quality holds significance in identifying potential hazards and implementing suitable management strategies. In this paper, a novel effort was made to determine the relative feature importance of a set of watershed characteristics (precipitation, temperature, urban land use, agricultural land use, and forest land-use factors) on four important water quality parameters (WQPs): fecal coliforms (FC), turbidity, pH, and conductivity of the Upper Green River watershed, Kentucky, USA. Random forest (RF), an ensemble learning method, was used to predict the WQPs from the causal parameters and determine the feature importance characteristics of the four WQPs previously mentioned. This model demonstrated that precipitation and temperature are the most influential factors on FC, turbidity, and pH. Forest land use and temperature are the two most important factors for conductivity. The novel feature importance factors of the RF model have likewise been confirmed for each WQP. In modeling stream WQPs, the developed the RF model outperformed the artificial neural network (ANN) model. Using the RF model, we obtain regression coefficients of (0.93, 0.74, and 0.94) for pH in training, testing, and overall. We obtain regression coefficients of (0.60, 0.64, and 0.61) using the ANN model. ⁠⁠⁠⁠⁠⁠⁠Overall, the RF model was more effective than the ANN model in modeling stream WQPs. The model identified precipitation and temperature as the most influential factors on FC, turbidity, and pH, while forest land use and temperature were the most important factors in determining conductivity. It is also found that land use factors are important to improve the accuracy of WQPs predictions from climate variables. The results of this study can be used by authorities to better understand and control pollution at the watershed scale. [ABSTRACT FROM AUTHOR]

Addressing the challenges of scalable and cost-effective energy performance analysis in mid to high-rise office buildings, this paper introduces a novel approach utilizing an inverse-based artificial neural network (ANN). This ANN was trained on synthetically generated heating and cooling load parameters – derived from simulations conducted in EnergyPlus – to predict characterization parameters, including the building envelope, internal heat gains, and HVAC operational parameters. Diverging from traditional forward surrogate models, this inverse surrogate model fills a critical gap in current building energy modeling approaches that are hindered by data and resource limitations. Its effectiveness is verified with a testing dataset of 3000 buildings and is further demonstrated through a case study in Ottawa, Ontario. Proving to be an efficient, cost-effective tool for energy retrofit screening, the model is enhanced by a user-friendly web-based application (Ferreira and Gunay), marking a significant advancement in accessible building energy analysis. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive review of the most recent papers and research trends in the fields of wind energy and artificial intelligence. Our study aims to guide future research by identifying the potential application and research areas of artificial intelligence and machine learning techniques in the wind energy sector and the knowledge gaps in this field. Artificial intelligence techniques offer significant benefits and advantages in many sub‐areas, such as increasing the efficiency of wind energy facilities, estimating energy production, optimizing operation and maintenance, providing security and control, data analysis, and management. Our research focuses on studies indexed in the Web of Science library on wind energy between 2000 and 2023 using sub‐branches of artificial intelligence techniques such as artificial neural networks, other machine learning methods, data mining, fuzzy logic, meta‐heuristics, and statistical methods. In this way, current methods and techniques in the literature are examined to produce more efficient, sustainable, and reliable wind energy, and the findings are discussed for future studies. This comprehensive evaluation is designed to be helpful to academics and specialists interested in acquiring a current and broad perspective on the types of uses of artificial intelligence in wind energy and seeking what research subjects are needed in this field. [ABSTRACT FROM AUTHOR]

The primary objective of the research presented in this article is to introduce an artificial neural network that demands less computational power than a conventional deep neural network. The development of this ANN was achieved through the application of Ordered Fuzzy Numbers (OFNs). In the context of Industry 4.0, there are numerous applications where this solution could be utilized for data processing. It allows the deployment of Artificial Intelligence at the network edge on small devices, eliminating the need to transfer large amounts of data to a cloud server for analysis. Such networks will be easier to implement in small-scale solutions, like those for the Internet of Things, in the future. This paper presents test results where a real system was monitored, and anomalies were detected and predicted. [ABSTRACT FROM AUTHOR]

Sea surface gage height (SSGH) data are commonly measured at sparsely deployed tidal stations while coastal resources management requires spatially distributed SSGH data. This paper presents three different machine learning models, including a Random Forest (RF) model, an Extreme Gradient Boosting (XGBoost) model, and an Artificial Neural Network (ANN) model, for retrieving and mapping spatially distributed SSGH. The models were originally developed and independently validated using 10 years of VIIRS satellite remote sensing data and corresponding in-situ gage height (GH) data within the MATLAB ANN toolbox and RStudio. The paper made two major new contributions to the determination of SSGH, including a scientific contribution and a technical contribution. Scientifically, this paper has provided new insights into important factors affecting SSGH. The SSGH varies significantly with the location (GPS coordinates) and Julian Day with both factors affecting the tide and thus SSGH. SSGH is also affected by sea surface waves that affect the reflectance of light from different wavelengths of satellite sensors, which are described with the VIIRS remote sensing reflectance (Rrs) bands including Rrs 410, 443, 486, 551, and 671. Technically, the machine learning models, particularly the ANN model, are capable of providing the most accurate and spatially distributed SSGH data particularly for coastal waters, as characterized by the model performance metrics including the correlation coefficient R value of 0.94 for training, 0.94 for validation, and 0.93 for testing and the low root mean square error (RMSE) value of 0.113 m for training, 0.113 m for validation, and 0.118 m for testing. [ABSTRACT FROM AUTHOR]

The present review paper addresses the increasing interest in the application of machine learning (ML) algorithms in the assessment of the fatigue response of additively manufactured (AM) metal alloys. This review aims to systematically collect, categorize, and analyze relevant research papers in this domain. The most commonly used ML algorithms are presented, discussing their specific relevance to the fatigue modeling of AM metal alloys. A detailed analysis of the most relevant input features used in the literature to predict the main parameters related to the fatigue response is provided. Each work has been analyzed to highlight its strengths and peculiarities, thereby offering insights into novel methodologies and approaches for addressing critical challenges within this field. Particular attention is dedicated to the role of defects and the related size‐effect, as they strongly influence the fatigue response. In conclusion, this review not only synthesizes existing knowledge but also offers forward‐looking recommendations for future research directions, providing a valuable resource for researchers in the domain of ML‐assisted fatigue assessment for AM metal alloys. [ABSTRACT FROM AUTHOR]

Saltwater intrusion is an essential problem in estuaries that can threaten the ecological environment, especially in high-salinity situations. Therefore in this paper, traditional multiple linear regression (MLR) and artificial neural network (ANN) modeling are applied to forecast overall and high salinity in the Lower Scheldt Estuary, Belgium. Mutual information (MI) and conditional mutual information (CMI) are used to select optimal driving forces (DFs), with the daily discharge (Q), daily water temperature (WT), and daily sea level (SL) selected as the main DFs. Next, we analyze whether applying a discrete wavelet transform (DWT) to remove the noise from the original time series improves the results. Here, the DWT is applied in Signal-hybrid (SH) and Within-hybrid (WH) frameworks. Both the MLR and ANN models demonstrate satisfactory performance in daily overall salinity simulation over the Scheldt Estuary. The relatively complex ANN models outperform MLR because of their capabilities of capturing complex interactions. Because the nonlinear relationship between salinity and DFs is variable at different locations, the performance of the MLR models in the midstream region is far inferior to that in the downstream region during spring and winter. The results reveal that the application of DWT enhances simulation of both overall and high salinity in this region, especially for the ANN model with the WH framework. With the effect of Q decline or SL rise, the salinity in the middle Scheldt Estuary increases more significantly, and the ANN models are more sensitive to these perturbations. [ABSTRACT FROM AUTHOR]

Along with seaports automation, there is growing interest in the automation of Grab-Type Ship Unloader (GTSU) that unloads coal and iron ore from bulk carriers. Autonomous unloading operations of GTSU offer the potential for significant productivity improvement and cost savings. In this paper, an AI model trained with manual operation data was designed for GTSU automation operation, and the AI model was verified through the equation-of-motion-based GTSU operation simulator. The operation data of hoist, grab, and trolley were predicted by training the designed AI model with the manual operation data of GTSU. Before applying the predicted data to the actual equipment, the predicted driving data was verified using the equation-of-motion-based GTSU operation simulator. The AI prediction model was designed using the Multi-Layer Perception network, a type of artificial neural network. The AI prediction model was evaluated with the Mean-Squared Error indicator, and the validation loss was found to be less than 0.02. In addition, verification of the prediction data was performed using the GTSU dynamics-based simulator. The Mean Relative Error was up to 0.50, and the R2 score value exceeded 0.92, indicating that the model is effective in predicting operation data. The proposed AI prediction model will be effectively utilized to implement a fully automated unloading system. [ABSTRACT FROM AUTHOR]